An interactive audio source separation framework based on non-negative matrix factorization
| Autor: | Joel Sirot, Alexey Ozerov, Ngoc Q. K. Duong, Louis Chevallier |
|---|---|
| Přispěvatelé: | Ozerov, Alexey |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
business.industry
Computer science [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing Separation (aeronautics) timefrequency annotation nonnegative matrix factorization Machine learning computer.software_genre Matrix decomposition Non-negative matrix factorization Constraint (information theory) Range (mathematics) user feedback uncertainty-based learning Source separation Spectrogram Interactive audio source separation Artificial intelligence Data mining business computer [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing |
| Zdroj: | ICASSP |
| Popis: | Though audio source separation offers a wide range of applications in audio enhancement and post-production, its performance has yet to reach the satisfactory especially for single-channel mixtures with limited training data. In this paper we present a novel interactive source separation framework that allows end-users to provide feedback at each separation step so as to gradually improve the result. For this purpose, a prototype graphical user interface (GUI) is developed to help users annotating time-frequency regions where a source can be labeled as either active, inactive, or well-separated within the displayed spectrogram. This user feedback information, which is partially new with respect to the state-of-the-art annotations, is then taken into account in a proposed uncertainty-based learning algorithm to constraint the source estimates in next separation step. The considered framework is based on non-negative matrix factorization and is shown to be effective even without using any isolated training data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|